Alert button
Picture for Francisco Sahli Costabal

Francisco Sahli Costabal

Alert button

Shape of my heart: Cardiac models through learned signed distance functions

Sep 05, 2023
Jan Verhülsdonk, Thomas Grandits, Francisco Sahli Costabal, Rolf Krause, Angelo Auricchio, Gundolf Haase, Simone Pezzuto, Alexander Effland

The efficient construction of an anatomical model is one of the major challenges of patient-specific in-silico models of the human heart. Current methods frequently rely on linear statistical models, allowing no advanced topological changes, or requiring medical image segmentation followed by a meshing pipeline, which strongly depends on image resolution, quality, and modality. These approaches are therefore limited in their transferability to other imaging domains. In this work, the cardiac shape is reconstructed by means of three-dimensional deep signed distance functions with Lipschitz regularity. For this purpose, the shapes of cardiac MRI reconstructions are learned from public databases to model the spatial relation of multiple chambers in Cartesian space. We demonstrate that this approach is also capable of reconstructing anatomical models from partial data, such as point clouds from a single ventricle, or modalities different from the trained MRI, such as electroanatomical mapping, and in addition, allows us to generate new anatomical shapes by randomly sampling latent vectors.

Viaarxiv icon

Physics-informed neural networks for blood flow inverse problems

Aug 02, 2023
Jeremias Garay, Jocelyn Dunstan, Sergio Uribe, Francisco Sahli Costabal

Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving inverse problems, especially in cases where no complete information about the system is known and scatter measurements are available. This is especially useful in hemodynamics since the boundary information is often difficult to model, and high-quality blood flow measurements are generally hard to obtain. In this work, we use the PINNs methodology for estimating reduced-order model parameters and the full velocity field from scatter 2D noisy measurements in the ascending aorta. The results show stable and accurate parameter estimations when using the method with simulated data, while the velocity reconstruction shows dependence on the measurement quality and the flow pattern complexity. The method allows for solving clinical-relevant inverse problems in hemodynamics and complex coupled physical systems.

Viaarxiv icon

Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields

Jul 24, 2023
Tabita Catalán, Matías Courdurier, Axel Osses, René Botnar, Francisco Sahli Costabal, Claudia Prieto

Figure 1 for Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields
Figure 2 for Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields
Figure 3 for Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields
Figure 4 for Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields

Cardiac cine MRI is the gold standard for cardiac functional assessment, but the inherently slow acquisition process creates the necessity of reconstruction approaches for accelerated undersampled acquisitions. Several regularization approaches that exploit spatial-temporal redundancy have been proposed to reconstruct undersampled cardiac cine MRI. More recently, methods based on supervised deep learning have been also proposed to further accelerate acquisition and reconstruction. However, these techniques rely on usually large dataset for training, which are not always available. In this work, we propose an unsupervised approach based on implicit neural field representations for cardiac cine MRI (so called NF-cMRI). The proposed method was evaluated in in-vivo undersampled golden-angle radial multi-coil acquisitions for undersampling factors of 26x and 52x, achieving good image quality, and comparable spatial and improved temporal depiction than a state-of-the-art reconstruction technique.

Viaarxiv icon

WarpPINN: Cine-MR image registration with physics-informed neural networks

Nov 22, 2022
Pablo Arratia López, Hernán Mella, Sergio Uribe, Daniel E. Hurtado, Francisco Sahli Costabal

Figure 1 for WarpPINN: Cine-MR image registration with physics-informed neural networks
Figure 2 for WarpPINN: Cine-MR image registration with physics-informed neural networks
Figure 3 for WarpPINN: Cine-MR image registration with physics-informed neural networks
Figure 4 for WarpPINN: Cine-MR image registration with physics-informed neural networks

Heart failure is typically diagnosed with a global function assessment, such as ejection fraction. However, these metrics have low discriminate power, failing to distinguish different types of this disease. Quantifying local deformations in the form of cardiac strain can provide helpful information, but it remains a challenge. In this work, we introduce WarpPINN, a physics-informed neural network to perform image registration to obtain local metrics of the heart deformation. We apply this method to cine magnetic resonance images to estimate the motion during the cardiac cycle. We inform our neural network of near-incompressibility of cardiac tissue by penalizing the jacobian of the deformation field. The loss function has two components: an intensity-based similarity term between the reference and the warped template images, and a regularizer that represents the hyperelastic behavior of the tissue. The architecture of the neural network allows us to easily compute the strain via automatic differentiation to assess cardiac activity. We use Fourier feature mappings to overcome the spectral bias of neural networks, allowing us to capture discontinuities in the strain field. We test our algorithm on a synthetic example and on a cine-MRI benchmark of 15 healthy volunteers. We outperform current methodologies both landmark tracking and strain estimation. We expect that WarpPINN will enable more precise diagnostics of heart failure based on local deformation information. Source code is available at https://github.com/fsahli/WarpPINN.

* 18 pages, 10 figures 
Viaarxiv icon

$Δ$-PINNs: physics-informed neural networks on complex geometries

Sep 08, 2022
Francisco Sahli Costabal, Simone Pezzuto, Paris Perdikaris

Figure 1 for $Δ$-PINNs: physics-informed neural networks on complex geometries
Figure 2 for $Δ$-PINNs: physics-informed neural networks on complex geometries
Figure 3 for $Δ$-PINNs: physics-informed neural networks on complex geometries
Figure 4 for $Δ$-PINNs: physics-informed neural networks on complex geometries

Physics-informed neural networks (PINNs) have demonstrated promise in solving forward and inverse problems involving partial differential equations. Despite recent progress on expanding the class of problems that can be tackled by PINNs, most of existing use-cases involve simple geometric domains. To date, there is no clear way to inform PINNs about the topology of the domain where the problem is being solved. In this work, we propose a novel positional encoding mechanism for PINNs based on the eigenfunctions of the Laplace-Beltrami operator. This technique allows to create an input space for the neural network that represents the geometry of a given object. We approximate the eigenfunctions as well as the operators involved in the partial differential equations with finite elements. We extensively test and compare the proposed methodology against traditional PINNs in complex shapes, such as a coil, a heat sink and a bunny, with different physics, such as the Eikonal equation and heat transfer. We also study the sensitivity of our method to the number of eigenfunctions used, as well as the discretization used for the eigenfunctions and the underlying operators. Our results show excellent agreement with the ground truth data in cases where traditional PINNs fail to produce a meaningful solution. We envision this new technique will expand the effectiveness of PINNs to more realistic applications.

* 15 pages, 8 figures 
Viaarxiv icon

Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifolds

Mar 11, 2022
Simone Pezzuto, Paris Perdikaris, Francisco Sahli Costabal

Figure 1 for Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifolds
Figure 2 for Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifolds
Figure 3 for Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifolds
Figure 4 for Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifolds

We propose a method for identifying an ectopic activation in the heart non-invasively. Ectopic activity in the heart can trigger deadly arrhythmias. The localization of the ectopic foci or earliest activation sites (EASs) is therefore a critical information for cardiologists in deciding the optimal treatment. In this work, we formulate the identification problem as a global optimization problem, by minimizing the mismatch between the ECG predicted by a cardiac model, when paced at a given EAS, and the observed ECG during the ectopic activity. Our cardiac model amounts at solving an anisotropic eikonal equation for cardiac activation and the forward bidomain model in the torso with the lead field approach for computing the ECG. We build a Gaussian process surrogate model of the loss function on the heart surface to perform Bayesian optimization. In this procedure, we iteratively evaluate the loss function following the lower confidence bound criterion, which combines exploring the surface with exploitation of the minimum region. We also extend this framework to incorporate multiple levels of fidelity of the model. We show that our procedure converges to the minimum only after $11.7\pm10.4$ iterations (20 independent runs) for the single-fidelity case and $3.5\pm1.7$ iterations for the multi-fidelity case. We envision that this tool could be applied in real time in a clinical setting to identify potentially dangerous EASs.

* 6 pages, 4 figures, Mathmod 2022 
Viaarxiv icon

Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps

Feb 01, 2022
Carlos Ruiz Herrera, Thomas Grandits, Gernot Plank, Paris Perdikaris, Francisco Sahli Costabal, Simone Pezzuto

Figure 1 for Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
Figure 2 for Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
Figure 3 for Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
Figure 4 for Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps

We propose FiberNet, a method to estimate in-vivo the cardiac fiber architecture of the human atria from multiple catheter recordings of the electrical activation. Cardiac fibers play a central rolein the electro-mechanical function of the heart, yet they aredifficult to determine in-vivo, and hence rarely truly patient-specificin existing cardiac models.FiberNet learns the fibers arrangement by solvingan inverse problem with physics-informed neural networks. The inverse problem amounts to identifyingthe conduction velocity tensor of a cardiac propagation modelfrom a set of sparse activation maps. The use of multiple mapsenables the simultaneous identification of all the componentsof the conduction velocity tensor, including the local fiber angle.We extensively test FiberNet on synthetic 2-D and 3-D examples, diffusion tensor fibers, and a patient-specific case. We show that 3 maps are sufficient to accurately capture the fibers, also in thepresence of noise. With fewer maps, the role of regularization becomesprominent. Moreover, we show that the fitted model can robustlyreproduce unseen activation maps. We envision that FiberNet will help the creation of patient-specific models for personalized medicine.The full code is available at http://github.com/fsahli/FiberNet.

* 28 pages, 11 figures 
Viaarxiv icon

Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification

Dec 16, 2021
Lia Gander, Simone Pezzuto, Ali Gharaviri, Rolf Krause, Paris Perdikaris, Francisco Sahli Costabal

Figure 1 for Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification
Figure 2 for Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification
Figure 3 for Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification
Figure 4 for Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification

Computational models of atrial fibrillation have successfully been used to predict optimal ablation sites. A critical step to assess the effect of an ablation pattern is to pace the model from different, potentially random, locations to determine whether arrhythmias can be induced in the atria. In this work, we propose to use multi-fidelity Gaussian process classification on Riemannian manifolds to efficiently determine the regions in the atria where arrhythmias are inducible. We build a probabilistic classifier that operates directly on the atrial surface. We take advantage of lower resolution models to explore the atrial surface and combine seamlessly with high-resolution models to identify regions of inducibility. When trained with 40 samples, our multi-fidelity classifier shows a balanced accuracy that is 10% higher than a nearest neighbor classifier used as a baseline atrial fibrillation model, and 9% higher in presence of atrial fibrillation with ablations. We hope that this new technique will allow faster and more precise clinical applications of computational models for atrial fibrillation.

* 22 pages, 7 figures 
Viaarxiv icon

Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks

Feb 22, 2021
Thomas Grandits, Simone Pezzuto, Francisco Sahli Costabal, Paris Perdikaris, Thomas Pock, Gernot Plank, Rolf Krause

Figure 1 for Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks
Figure 2 for Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks
Figure 3 for Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks

Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information can be extracted from the available data. The fibers in cardiac tissue conduct the electrical wave faster, and their direction could be inferred from activation times. In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation. In particular, we train the neural network to weakly satisfy the anisotropic eikonal equation and to predict the measured activation times. We use a local basis for the anisotropic conductivity tensor, which encodes the fiber orientation. The methodology is tested both in a synthetic example and for patient data. Our approach shows good agreement in both cases and it outperforms a state of the art method in the patient data. The results show a first step towards learning the fiber orientations from electroanatomical maps with physics-informed neural networks.

* 8 pages, 2 figures 
Viaarxiv icon